Análisis de modelos SOM - Frecuencia datos de entrada: mes

Modelo

• ID: 330
• Descripción:
• Frecuencia: mes
• Variables: fecha_cnt, tmax, tmin, precip
• Dimensiones del mapa: 5,5
• Iteraciones: 10000
• Parámetros adicionales:

source("../../lib/som-utils.R")

Attaching package: 'dplyr'

The following objects are masked from 'package:stats':

    filter, lag

The following objects are masked from 'package:base':

    intersect, setdiff, setequal, union

source("../../lib/maps-utils.R")

Linking to GEOS 3.8.0, GDAL 3.0.4, PROJ 6.3.1

Carga del modelo desde disco

mpr.set_base_path_analysis()
model <- mpr.load_model("som-330.rds.xz")
summary(model)

SOM of size 5x5 with a hexagonal topology and a bubble neighbourhood function.
The number of data layers is 1.
Distance measure(s) used: sumofsquares.
Training data included: 94881 objects.
Mean distance to the closest unit in the map: 0.417.

plot(model, type="changes")

Carga del dataset de entrada

df <- mpr.load_data("datos_mes.csv.xz")

df

summary(df)

 id_estacion           fecha             fecha_cnt           tmax      
 Length:94881       Length:94881       Min.   : 1.000   Min.   :-53.0  
 Class :character   Class :character   1st Qu.: 4.000   1st Qu.:148.0  
 Mode  :character   Mode  :character   Median : 6.000   Median :198.0  
                                       Mean   : 6.497   Mean   :200.2  
                                       3rd Qu.: 9.000   3rd Qu.:255.0  
                                       Max.   :12.000   Max.   :403.0  
      tmin             precip           nevada           prof_nieve      
 Min.   :-121.00   Min.   :  0.00   Min.   :0.000000   Min.   :   0.000  
 1st Qu.:  53.00   1st Qu.:  3.00   1st Qu.:0.000000   1st Qu.:   0.000  
 Median :  98.00   Median : 10.00   Median :0.000000   Median :   0.000  
 Mean   :  98.86   Mean   : 16.25   Mean   :0.000295   Mean   :   0.467  
 3rd Qu.: 148.00   3rd Qu.: 22.00   3rd Qu.:0.000000   3rd Qu.:   0.000  
 Max.   : 254.00   Max.   :422.00   Max.   :6.000000   Max.   :1834.000  
    longitud        latitud            altitud      
 Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:38.28   1st Qu.: -5.6417   1st Qu.:  42.0  
 Median :40.82   Median : -3.4500   Median : 247.0  
 Mean   :39.66   Mean   : -3.4350   Mean   : 418.5  
 3rd Qu.:42.08   3rd Qu.:  0.4914   3rd Qu.: 656.0  
 Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

Carga de los mapas

world <- ne_countries(scale = "medium", returnclass = "sf")
spain <- subset(world, admin == "Spain")

Mapa de densidad

plot(model, type="count", shape = "straight", palette.name = mpr.degrade.bleu)

Número de elementos en cada celda:

nb <- table(model$unit.classif)
print(nb)

   1    2    3    4    5    6    7    8    9   10   11   12   13   14   15   16 
 678  141 2112 3696 3455  801 2301  845 1845 4964 2898 4506 3437 3840 4888 4606 
  17   18   19   20   21   22   23   24   25 
7021 5917 5431 5758 7052 5979 2450 4647 5613 

Comprobación de nodos vacíos:

dim_model <- 5*5;
len_nb = length(nb);
empty_nodes <- dim_model != len_nb;
if (empty_nodes) {
  print(paste("[Warning] Existen nodos vacíos: ", len_nb, "/", dim_model))
}

Mapa de distancia entre vecinos

plot(model, type="dist.neighbours", shape = "straight")

Influencia de las variables

model_colnames = c("fecha_cnt", "tmax", "tmin", "precip")
model_ncol = length(model_colnames)

Mapa de variables.

plot(model, shape = "straight")

Mapa de calor por variable

par(mfrow=c(3,4))
for (j in 1:model_ncol) {
  plot(model, type="property", property=getCodes(model,1)[,j],
    palette.name=mpr.coolBlueHotRed,
    main=model_colnames[j],
    cex=0.5, shape = "straight")
}

Correlación para cada columna del vector de nodos

if (!empty_nodes) {
  cor <- apply(getCodes(model,1), 2, mpr.weighted.correlation, w=nb, som=model)
  print(cor)
}

      fecha_cnt      tmax      tmin     precip
[1,]  0.8288650 0.4752482 0.5407294 -0.1747099
[2,] -0.5027039 0.5313997 0.4277294 -0.5969889

Representación de cada variable en un mapa de factores:

if (!empty_nodes) {
  par(mfrow=c(1,1))
  plot(cor[1,], cor[2,], xlim=c(-1,1), ylim=c(-1,1), type="n")
  lines(c(-1,1),c(0,0))
  lines(c(0,0),c(-1,1))
  text(cor[1,], cor[2,], labels=model_colnames, cex=0.75)
  symbols(0,0,circles=1,inches=F,add=T)
}

Importancia de cada variable - varianza ponderada por el tamaño de la celda:

if (!empty_nodes) {
  sigma2 <- sqrt(apply(getCodes(model,1),2,function(x,effectif)
     {m<-sum(effectif*(x-weighted.mean(x,effectif))^2)/(sum(effectif)-1)},
     effectif=nb))
  print(sort(sigma2,decreasing=T))
}

     tmax fecha_cnt      tmin    precip 
0.9604371 0.9588291 0.9531512 0.9277726 

Clustering

if (!empty_nodes) {
  hac <- mpr.hac(model, nb)
}

Visualización de 3 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=3)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=3)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin             precip      
 Min.   : 1.000   Min.   :-42.0   Min.   :-108.00   Min.   : 41.00  
 1st Qu.: 8.000   1st Qu.:140.0   1st Qu.:  72.00   1st Qu.: 58.00  
 Median :10.000   Median :172.0   Median :  99.00   Median : 76.00  
 Mean   : 8.671   Mean   :170.6   Mean   :  96.87   Mean   : 81.19  
 3rd Qu.:11.000   3rd Qu.:204.0   3rd Qu.: 125.00   3rd Qu.: 94.00  
 Max.   :12.000   Max.   :350.0   Max.   : 223.00   Max.   :422.00  
     nevada    prof_nieve        longitud        latitud       
 Min.   :0   Min.   :  0.00   Min.   :27.82   Min.   :-17.889  
 1st Qu.:0   1st Qu.:  0.00   1st Qu.:40.70   1st Qu.: -8.411  
 Median :0   Median :  0.00   Median :42.33   Median : -4.010  
 Mean   :0   Mean   :  1.69   Mean   :41.11   Mean   : -4.302  
 3rd Qu.:0   3rd Qu.:  0.00   3rd Qu.:43.31   3rd Qu.: -1.787  
 Max.   :0   Max.   :892.00   Max.   :43.57   Max.   :  4.216  
    altitud      
 Min.   :   1.0  
 1st Qu.:  32.0  
 Median :  98.0  
 Mean   : 286.4  
 3rd Qu.: 336.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin             precip     
 Min.   : 1.000   Min.   :-53.0   Min.   :-121.00   Min.   : 0.00  
 1st Qu.: 2.000   1st Qu.:122.0   1st Qu.:  27.00   1st Qu.: 6.00  
 Median : 4.000   Median :156.0   Median :  58.00   Median :14.00  
 Mean   : 5.868   Mean   :151.2   Mean   :  54.64   Mean   :18.08  
 3rd Qu.:11.000   3rd Qu.:184.0   3rd Qu.:  84.00   3rd Qu.:27.00  
 Max.   :12.000   Max.   :281.0   Max.   : 177.00   Max.   :93.00  
     nevada           prof_nieve           longitud        latitud        
 Min.   :0.000000   Min.   :   0.0000   Min.   :27.82   Min.   :-17.8889  
 1st Qu.:0.000000   1st Qu.:   0.0000   1st Qu.:39.49   1st Qu.: -4.8500  
 Median :0.000000   Median :   0.0000   Median :41.11   Median : -2.7331  
 Mean   :0.000541   Mean   :   0.7399   Mean   :40.48   Mean   : -2.7774  
 3rd Qu.:0.000000   3rd Qu.:   0.0000   3rd Qu.:42.33   3rd Qu.:  0.4942  
 Max.   :6.000000   Max.   :1834.0000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  69.0  
 Median : 427.0  
 Mean   : 527.8  
 3rd Qu.: 775.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax            tmin           precip           nevada 
 Min.   : 1.000   Min.   : 87.0   Min.   : 56.0   Min.   : 0.000   Min.   :0  
 1st Qu.: 6.000   1st Qu.:236.0   1st Qu.:132.0   1st Qu.: 1.000   1st Qu.:0  
 Median : 7.000   Median :265.0   Median :155.0   Median : 5.000   Median :0  
 Mean   : 7.125   Mean   :266.8   Mean   :156.8   Mean   : 8.109   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:295.0   3rd Qu.:181.0   3rd Qu.:12.000   3rd Qu.:0  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :60.000   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:37.18   1st Qu.: -6.0556   1st Qu.:  32.0  
 Median : 0.00000   Median :39.86   Median : -3.6781   Median :  87.0  
 Mean   : 0.00247   Mean   :38.47   Mean   : -4.2166   Mean   : 287.6  
 3rd Qu.: 0.00000   3rd Qu.:41.62   3rd Qu.:  0.3664   3rd Qu.: 540.0  
 Max.   :35.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2371.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

Visualización de 4 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=4)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=4)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin             precip      
 Min.   : 1.000   Min.   :-42.0   Min.   :-108.00   Min.   : 41.00  
 1st Qu.: 8.000   1st Qu.:140.0   1st Qu.:  72.00   1st Qu.: 58.00  
 Median :10.000   Median :172.0   Median :  99.00   Median : 76.00  
 Mean   : 8.671   Mean   :170.6   Mean   :  96.87   Mean   : 81.19  
 3rd Qu.:11.000   3rd Qu.:204.0   3rd Qu.: 125.00   3rd Qu.: 94.00  
 Max.   :12.000   Max.   :350.0   Max.   : 223.00   Max.   :422.00  
     nevada    prof_nieve        longitud        latitud       
 Min.   :0   Min.   :  0.00   Min.   :27.82   Min.   :-17.889  
 1st Qu.:0   1st Qu.:  0.00   1st Qu.:40.70   1st Qu.: -8.411  
 Median :0   Median :  0.00   Median :42.33   Median : -4.010  
 Mean   :0   Mean   :  1.69   Mean   :41.11   Mean   : -4.302  
 3rd Qu.:0   3rd Qu.:  0.00   3rd Qu.:43.31   3rd Qu.: -1.787  
 Max.   :0   Max.   :892.00   Max.   :43.57   Max.   :  4.216  
    altitud      
 Min.   :   1.0  
 1st Qu.:  32.0  
 Median :  98.0  
 Mean   : 286.4  
 3rd Qu.: 336.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin             precip     
 Min.   : 7.00   Min.   :-24.0   Min.   :-110.00   Min.   : 0.00  
 1st Qu.:10.00   1st Qu.:119.0   1st Qu.:  32.00   1st Qu.: 5.00  
 Median :11.00   Median :156.0   Median :  63.00   Median :13.00  
 Mean   :10.99   Mean   :152.8   Mean   :  59.74   Mean   :17.13  
 3rd Qu.:12.00   3rd Qu.:189.0   3rd Qu.:  91.00   3rd Qu.:26.00  
 Max.   :12.00   Max.   :271.0   Max.   : 157.00   Max.   :88.00  
     nevada            prof_nieve          longitud        latitud        
 Min.   :0.0000000   Min.   :  0.0000   Min.   :27.92   Min.   :-17.7550  
 1st Qu.:0.0000000   1st Qu.:  0.0000   1st Qu.:39.49   1st Qu.: -4.8500  
 Median :0.0000000   Median :  0.0000   Median :41.11   Median : -2.6544  
 Mean   :0.0004708   Mean   :  0.2687   Mean   :40.45   Mean   : -2.7321  
 3rd Qu.:0.0000000   3rd Qu.:  0.0000   3rd Qu.:42.24   3rd Qu.:  0.4942  
 Max.   :3.0000000   Max.   :382.0000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  85.0  
 Median : 513.0  
 Mean   : 572.5  
 3rd Qu.: 790.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax            tmin             precip     
 Min.   :1.000   Min.   :-53.0   Min.   :-121.00   Min.   : 0.00  
 1st Qu.:2.000   1st Qu.:124.0   1st Qu.:  25.00   1st Qu.: 6.00  
 Median :3.000   Median :156.0   Median :  55.00   Median :15.00  
 Mean   :2.864   Mean   :150.3   Mean   :  51.65   Mean   :18.64  
 3rd Qu.:4.000   3rd Qu.:182.0   3rd Qu.:  81.00   3rd Qu.:27.00  
 Max.   :7.000   Max.   :281.0   Max.   : 177.00   Max.   :93.00  
     nevada           prof_nieve          longitud        latitud        
 Min.   :0.000000   Min.   :   0.000   Min.   :27.82   Min.   :-17.8889  
 1st Qu.:0.000000   1st Qu.:   0.000   1st Qu.:39.48   1st Qu.: -5.3456  
 Median :0.000000   Median :   0.000   Median :41.15   Median : -2.7331  
 Mean   :0.000582   Mean   :   1.016   Mean   :40.49   Mean   : -2.8040  
 3rd Qu.:0.000000   3rd Qu.:   0.000   3rd Qu.:42.36   3rd Qu.:  0.4942  
 Max.   :6.000000   Max.   :1834.000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  64.0  
 Median : 370.0  
 Mean   : 501.6  
 3rd Qu.: 735.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt           tmax            tmin           precip           nevada 
 Min.   : 1.000   Min.   : 87.0   Min.   : 56.0   Min.   : 0.000   Min.   :0  
 1st Qu.: 6.000   1st Qu.:236.0   1st Qu.:132.0   1st Qu.: 1.000   1st Qu.:0  
 Median : 7.000   Median :265.0   Median :155.0   Median : 5.000   Median :0  
 Mean   : 7.125   Mean   :266.8   Mean   :156.8   Mean   : 8.109   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:295.0   3rd Qu.:181.0   3rd Qu.:12.000   3rd Qu.:0  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :60.000   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:37.18   1st Qu.: -6.0556   1st Qu.:  32.0  
 Median : 0.00000   Median :39.86   Median : -3.6781   Median :  87.0  
 Mean   : 0.00247   Mean   :38.47   Mean   : -4.2166   Mean   : 287.6  
 3rd Qu.: 0.00000   3rd Qu.:41.62   3rd Qu.:  0.3664   3rd Qu.: 540.0  
 Max.   :35.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2371.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

Visualización de 5 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=5)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=5)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin             precip      
 Min.   : 1.000   Min.   :-42.0   Min.   :-108.00   Min.   : 41.00  
 1st Qu.: 8.000   1st Qu.:142.0   1st Qu.:  74.00   1st Qu.: 58.00  
 Median :10.000   Median :174.0   Median : 100.00   Median : 75.00  
 Mean   : 8.708   Mean   :171.9   Mean   :  97.71   Mean   : 76.92  
 3rd Qu.:11.000   3rd Qu.:205.0   3rd Qu.: 126.00   3rd Qu.: 91.00  
 Max.   :12.000   Max.   :336.0   Max.   : 219.00   Max.   :149.00  
     nevada    prof_nieve        longitud        latitud       
 Min.   :0   Min.   :  0.00   Min.   :27.82   Min.   :-17.889  
 1st Qu.:0   1st Qu.:  0.00   1st Qu.:40.63   1st Qu.: -8.372  
 Median :0   Median :  0.00   Median :42.34   Median : -4.010  
 Mean   :0   Mean   :  1.52   Mean   :41.11   Mean   : -4.212  
 3rd Qu.:0   3rd Qu.:  0.00   3rd Qu.:43.31   3rd Qu.: -1.787  
 Max.   :0   Max.   :892.00   Max.   :43.57   Max.   :  4.216  
    altitud       
 Min.   :   1.00  
 1st Qu.:  31.25  
 Median :  95.00  
 Mean   : 279.32  
 3rd Qu.: 287.00  
 Max.   :2535.00  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin            precip          nevada 
 Min.   : 1.000   Min.   : -8.0   Min.   :-58.00   Min.   :142.0   Min.   :0  
 1st Qu.: 3.000   1st Qu.:113.0   1st Qu.: 52.00   1st Qu.:152.0   1st Qu.:0  
 Median :10.000   Median :131.0   Median : 75.00   Median :167.0   Median :0  
 Mean   : 7.787   Mean   :139.5   Mean   : 76.75   Mean   :183.2   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:154.0   3rd Qu.: 92.00   3rd Qu.:196.0   3rd Qu.:0  
 Max.   :12.000   Max.   :350.0   Max.   :223.00   Max.   :422.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:40.80   1st Qu.: -8.624   1st Qu.:  68.6  
 Median :  0.000   Median :42.24   Median : -8.411   Median : 261.0  
 Mean   :  5.752   Mean   :41.06   Mean   : -6.466   Mean   : 455.1  
 3rd Qu.:  0.000   3rd Qu.:42.89   3rd Qu.: -3.831   3rd Qu.: 370.0  
 Max.   :607.000   Max.   :43.49   Max.   :  2.825   Max.   :2400.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax            tmin             precip     
 Min.   : 7.00   Min.   :-24.0   Min.   :-110.00   Min.   : 0.00  
 1st Qu.:10.00   1st Qu.:119.0   1st Qu.:  32.00   1st Qu.: 5.00  
 Median :11.00   Median :156.0   Median :  63.00   Median :13.00  
 Mean   :10.99   Mean   :152.8   Mean   :  59.74   Mean   :17.13  
 3rd Qu.:12.00   3rd Qu.:189.0   3rd Qu.:  91.00   3rd Qu.:26.00  
 Max.   :12.00   Max.   :271.0   Max.   : 157.00   Max.   :88.00  
     nevada            prof_nieve          longitud        latitud        
 Min.   :0.0000000   Min.   :  0.0000   Min.   :27.92   Min.   :-17.7550  
 1st Qu.:0.0000000   1st Qu.:  0.0000   1st Qu.:39.49   1st Qu.: -4.8500  
 Median :0.0000000   Median :  0.0000   Median :41.11   Median : -2.6544  
 Mean   :0.0004708   Mean   :  0.2687   Mean   :40.45   Mean   : -2.7321  
 3rd Qu.:0.0000000   3rd Qu.:  0.0000   3rd Qu.:42.24   3rd Qu.:  0.4942  
 Max.   :3.0000000   Max.   :382.0000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  85.0  
 Median : 513.0  
 Mean   : 572.5  
 3rd Qu.: 790.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin             precip     
 Min.   :1.000   Min.   :-53.0   Min.   :-121.00   Min.   : 0.00  
 1st Qu.:2.000   1st Qu.:124.0   1st Qu.:  25.00   1st Qu.: 6.00  
 Median :3.000   Median :156.0   Median :  55.00   Median :15.00  
 Mean   :2.864   Mean   :150.3   Mean   :  51.65   Mean   :18.64  
 3rd Qu.:4.000   3rd Qu.:182.0   3rd Qu.:  81.00   3rd Qu.:27.00  
 Max.   :7.000   Max.   :281.0   Max.   : 177.00   Max.   :93.00  
     nevada           prof_nieve          longitud        latitud        
 Min.   :0.000000   Min.   :   0.000   Min.   :27.82   Min.   :-17.8889  
 1st Qu.:0.000000   1st Qu.:   0.000   1st Qu.:39.48   1st Qu.: -5.3456  
 Median :0.000000   Median :   0.000   Median :41.15   Median : -2.7331  
 Mean   :0.000582   Mean   :   1.016   Mean   :40.49   Mean   : -2.8040  
 3rd Qu.:0.000000   3rd Qu.:   0.000   3rd Qu.:42.36   3rd Qu.:  0.4942  
 Max.   :6.000000   Max.   :1834.000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  64.0  
 Median : 370.0  
 Mean   : 501.6  
 3rd Qu.: 735.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt           tmax            tmin           precip           nevada 
 Min.   : 1.000   Min.   : 87.0   Min.   : 56.0   Min.   : 0.000   Min.   :0  
 1st Qu.: 6.000   1st Qu.:236.0   1st Qu.:132.0   1st Qu.: 1.000   1st Qu.:0  
 Median : 7.000   Median :265.0   Median :155.0   Median : 5.000   Median :0  
 Mean   : 7.125   Mean   :266.8   Mean   :156.8   Mean   : 8.109   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:295.0   3rd Qu.:181.0   3rd Qu.:12.000   3rd Qu.:0  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :60.000   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:37.18   1st Qu.: -6.0556   1st Qu.:  32.0  
 Median : 0.00000   Median :39.86   Median : -3.6781   Median :  87.0  
 Mean   : 0.00247   Mean   :38.47   Mean   : -4.2166   Mean   : 287.6  
 3rd Qu.: 0.00000   3rd Qu.:41.62   3rd Qu.:  0.3664   3rd Qu.: 540.0  
 Max.   :35.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2371.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

Visualización de 6 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=6)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=6)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax            tmin             precip           nevada 
 Min.   :1.000   Min.   :-42.0   Min.   :-108.00   Min.   : 73.00   Min.   :0  
 1st Qu.:1.000   1st Qu.:109.0   1st Qu.:  38.25   1st Qu.: 81.00   1st Qu.:0  
 Median :2.000   Median :127.0   Median :  59.00   Median : 90.00   Median :0  
 Mean   :2.445   Mean   :126.5   Mean   :  57.15   Mean   : 94.87   Mean   :0  
 3rd Qu.:4.000   3rd Qu.:152.0   3rd Qu.:  80.00   3rd Qu.:104.00   3rd Qu.:0  
 Max.   :6.000   Max.   :239.0   Max.   : 170.00   Max.   :149.00   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :  0.000   Min.   :27.92   Min.   :-17.755   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:41.84   1st Qu.: -8.419   1st Qu.:  42.0  
 Median :  0.000   Median :42.44   Median : -5.645   Median : 251.0  
 Mean   :  6.524   Mean   :41.50   Mean   : -5.291   Mean   : 439.6  
 3rd Qu.:  0.000   3rd Qu.:43.30   3rd Qu.: -2.039   3rd Qu.: 370.0  
 Max.   :892.000   Max.   :43.57   Max.   :  3.182   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin            precip          nevada 
 Min.   : 1.000   Min.   : -8.0   Min.   :-58.00   Min.   :142.0   Min.   :0  
 1st Qu.: 3.000   1st Qu.:113.0   1st Qu.: 52.00   1st Qu.:152.0   1st Qu.:0  
 Median :10.000   Median :131.0   Median : 75.00   Median :167.0   Median :0  
 Mean   : 7.787   Mean   :139.5   Mean   : 76.75   Mean   :183.2   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:154.0   3rd Qu.: 92.00   3rd Qu.:196.0   3rd Qu.:0  
 Max.   :12.000   Max.   :350.0   Max.   :223.00   Max.   :422.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:40.80   1st Qu.: -8.624   1st Qu.:  68.6  
 Median :  0.000   Median :42.24   Median : -8.411   Median : 261.0  
 Mean   :  5.752   Mean   :41.06   Mean   : -6.466   Mean   : 455.1  
 3rd Qu.:  0.000   3rd Qu.:42.89   3rd Qu.: -3.831   3rd Qu.: 370.0  
 Max.   :607.000   Max.   :43.49   Max.   :  2.825   Max.   :2400.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax            tmin             precip     
 Min.   : 7.00   Min.   :-24.0   Min.   :-110.00   Min.   : 0.00  
 1st Qu.:10.00   1st Qu.:119.0   1st Qu.:  32.00   1st Qu.: 5.00  
 Median :11.00   Median :156.0   Median :  63.00   Median :13.00  
 Mean   :10.99   Mean   :152.8   Mean   :  59.74   Mean   :17.13  
 3rd Qu.:12.00   3rd Qu.:189.0   3rd Qu.:  91.00   3rd Qu.:26.00  
 Max.   :12.00   Max.   :271.0   Max.   : 157.00   Max.   :88.00  
     nevada            prof_nieve          longitud        latitud        
 Min.   :0.0000000   Min.   :  0.0000   Min.   :27.92   Min.   :-17.7550  
 1st Qu.:0.0000000   1st Qu.:  0.0000   1st Qu.:39.49   1st Qu.: -4.8500  
 Median :0.0000000   Median :  0.0000   Median :41.11   Median : -2.6544  
 Mean   :0.0004708   Mean   :  0.2687   Mean   :40.45   Mean   : -2.7321  
 3rd Qu.:0.0000000   3rd Qu.:  0.0000   3rd Qu.:42.24   3rd Qu.:  0.4942  
 Max.   :3.0000000   Max.   :382.0000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  85.0  
 Median : 513.0  
 Mean   : 572.5  
 3rd Qu.: 790.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin             precip     
 Min.   :1.000   Min.   :-53.0   Min.   :-121.00   Min.   : 0.00  
 1st Qu.:2.000   1st Qu.:124.0   1st Qu.:  25.00   1st Qu.: 6.00  
 Median :3.000   Median :156.0   Median :  55.00   Median :15.00  
 Mean   :2.864   Mean   :150.3   Mean   :  51.65   Mean   :18.64  
 3rd Qu.:4.000   3rd Qu.:182.0   3rd Qu.:  81.00   3rd Qu.:27.00  
 Max.   :7.000   Max.   :281.0   Max.   : 177.00   Max.   :93.00  
     nevada           prof_nieve          longitud        latitud        
 Min.   :0.000000   Min.   :   0.000   Min.   :27.82   Min.   :-17.8889  
 1st Qu.:0.000000   1st Qu.:   0.000   1st Qu.:39.48   1st Qu.: -5.3456  
 Median :0.000000   Median :   0.000   Median :41.15   Median : -2.7331  
 Mean   :0.000582   Mean   :   1.016   Mean   :40.49   Mean   : -2.8040  
 3rd Qu.:0.000000   3rd Qu.:   0.000   3rd Qu.:42.36   3rd Qu.:  0.4942  
 Max.   :6.000000   Max.   :1834.000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  64.0  
 Median : 370.0  
 Mean   : 501.6  
 3rd Qu.: 735.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax            tmin           precip           nevada 
 Min.   : 4.00   Min.   :  2.0   Min.   :-53.0   Min.   : 41.00   Min.   :0  
 1st Qu.:10.00   1st Qu.:155.0   1st Qu.: 86.0   1st Qu.: 55.00   1st Qu.:0  
 Median :10.00   Median :184.5   Median :109.0   Median : 66.00   Median :0  
 Mean   :10.29   Mean   :183.3   Mean   :107.9   Mean   : 72.39   Mean   :0  
 3rd Qu.:11.00   3rd Qu.:213.0   3rd Qu.:132.0   3rd Qu.: 85.00   3rd Qu.:0  
 Max.   :12.00   Max.   :336.0   Max.   :219.0   Max.   :144.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   :  0.0000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.0000   1st Qu.:39.85   1st Qu.: -6.949   1st Qu.:  27.0  
 Median :  0.0000   Median :42.27   Median : -3.831   Median :  87.0  
 Mean   :  0.2584   Mean   :41.02   Mean   : -3.940   Mean   : 238.9  
 3rd Qu.:  0.0000   3rd Qu.:43.31   3rd Qu.: -0.558   3rd Qu.: 261.0  
 Max.   :114.0000   Max.   :43.57   Max.   :  4.216   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt           tmax            tmin           precip           nevada 
 Min.   : 1.000   Min.   : 87.0   Min.   : 56.0   Min.   : 0.000   Min.   :0  
 1st Qu.: 6.000   1st Qu.:236.0   1st Qu.:132.0   1st Qu.: 1.000   1st Qu.:0  
 Median : 7.000   Median :265.0   Median :155.0   Median : 5.000   Median :0  
 Mean   : 7.125   Mean   :266.8   Mean   :156.8   Mean   : 8.109   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:295.0   3rd Qu.:181.0   3rd Qu.:12.000   3rd Qu.:0  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :60.000   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:37.18   1st Qu.: -6.0556   1st Qu.:  32.0  
 Median : 0.00000   Median :39.86   Median : -3.6781   Median :  87.0  
 Mean   : 0.00247   Mean   :38.47   Mean   : -4.2166   Mean   : 287.6  
 3rd Qu.: 0.00000   3rd Qu.:41.62   3rd Qu.:  0.3664   3rd Qu.: 540.0  
 Max.   :35.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2371.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

Visualización de 8 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=8)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=8)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)
  df.cluster07 <- subset(df, cluster==7)
  df.cluster08 <- subset(df, cluster==8)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster07 <- select(df.cluster07, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster08 <- select(df.cluster08, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax            tmin             precip           nevada 
 Min.   :1.000   Min.   :-42.0   Min.   :-108.00   Min.   : 73.00   Min.   :0  
 1st Qu.:1.000   1st Qu.:109.0   1st Qu.:  38.25   1st Qu.: 81.00   1st Qu.:0  
 Median :2.000   Median :127.0   Median :  59.00   Median : 90.00   Median :0  
 Mean   :2.445   Mean   :126.5   Mean   :  57.15   Mean   : 94.87   Mean   :0  
 3rd Qu.:4.000   3rd Qu.:152.0   3rd Qu.:  80.00   3rd Qu.:104.00   3rd Qu.:0  
 Max.   :6.000   Max.   :239.0   Max.   : 170.00   Max.   :149.00   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :  0.000   Min.   :27.92   Min.   :-17.755   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:41.84   1st Qu.: -8.419   1st Qu.:  42.0  
 Median :  0.000   Median :42.44   Median : -5.645   Median : 251.0  
 Mean   :  6.524   Mean   :41.50   Mean   : -5.291   Mean   : 439.6  
 3rd Qu.:  0.000   3rd Qu.:43.30   3rd Qu.: -2.039   3rd Qu.: 370.0  
 Max.   :892.000   Max.   :43.57   Max.   :  3.182   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin            precip          nevada 
 Min.   : 1.000   Min.   : -8.0   Min.   :-58.00   Min.   :142.0   Min.   :0  
 1st Qu.: 3.000   1st Qu.:113.0   1st Qu.: 52.00   1st Qu.:152.0   1st Qu.:0  
 Median :10.000   Median :131.0   Median : 75.00   Median :167.0   Median :0  
 Mean   : 7.787   Mean   :139.5   Mean   : 76.75   Mean   :183.2   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:154.0   3rd Qu.: 92.00   3rd Qu.:196.0   3rd Qu.:0  
 Max.   :12.000   Max.   :350.0   Max.   :223.00   Max.   :422.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:40.80   1st Qu.: -8.624   1st Qu.:  68.6  
 Median :  0.000   Median :42.24   Median : -8.411   Median : 261.0  
 Mean   :  5.752   Mean   :41.06   Mean   : -6.466   Mean   : 455.1  
 3rd Qu.:  0.000   3rd Qu.:42.89   3rd Qu.: -3.831   3rd Qu.: 370.0  
 Max.   :607.000   Max.   :43.49   Max.   :  2.825   Max.   :2400.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax            tmin             precip     
 Min.   : 7.00   Min.   :-24.0   Min.   :-110.00   Min.   : 0.00  
 1st Qu.:10.00   1st Qu.:119.0   1st Qu.:  32.00   1st Qu.: 5.00  
 Median :11.00   Median :156.0   Median :  63.00   Median :13.00  
 Mean   :10.99   Mean   :152.8   Mean   :  59.74   Mean   :17.13  
 3rd Qu.:12.00   3rd Qu.:189.0   3rd Qu.:  91.00   3rd Qu.:26.00  
 Max.   :12.00   Max.   :271.0   Max.   : 157.00   Max.   :88.00  
     nevada            prof_nieve          longitud        latitud        
 Min.   :0.0000000   Min.   :  0.0000   Min.   :27.92   Min.   :-17.7550  
 1st Qu.:0.0000000   1st Qu.:  0.0000   1st Qu.:39.49   1st Qu.: -4.8500  
 Median :0.0000000   Median :  0.0000   Median :41.11   Median : -2.6544  
 Mean   :0.0004708   Mean   :  0.2687   Mean   :40.45   Mean   : -2.7321  
 3rd Qu.:0.0000000   3rd Qu.:  0.0000   3rd Qu.:42.24   3rd Qu.:  0.4942  
 Max.   :3.0000000   Max.   :382.0000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  85.0  
 Median : 513.0  
 Mean   : 572.5  
 3rd Qu.: 790.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax             tmin             precip       nevada 
 Min.   :1.000   Min.   :-53.00   Min.   :-121.00   Min.   : 1   Min.   :0  
 1st Qu.:1.000   1st Qu.:  5.00   1st Qu.: -56.00   1st Qu.:28   1st Qu.:0  
 Median :2.000   Median : 28.00   Median : -38.00   Median :39   Median :0  
 Mean   :2.498   Mean   : 25.85   Mean   : -40.17   Mean   :41   Mean   :0  
 3rd Qu.:3.000   3rd Qu.: 49.00   3rd Qu.: -20.00   3rd Qu.:52   3rd Qu.:0  
 Max.   :6.000   Max.   : 98.00   Max.   :  16.00   Max.   :93   Max.   :0  
   prof_nieve         longitud        latitud            altitud    
 Min.   :   0.00   Min.   :28.31   Min.   :-16.4992   Min.   :  42  
 1st Qu.:   0.00   1st Qu.:40.84   1st Qu.: -4.0103   1st Qu.:1894  
 Median :   0.00   Median :42.47   Median :  0.8842   Median :2230  
 Mean   :  29.99   Mean   :41.66   Mean   : -0.7733   Mean   :2034  
 3rd Qu.:   0.00   3rd Qu.:42.64   3rd Qu.:  1.3656   3rd Qu.:2371  
 Max.   :1834.00   Max.   :43.46   Max.   :  2.4803   Max.   :2535  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax            tmin            precip         nevada 
 Min.   :1.000   Min.   : 63.0   Min.   :-11.00   Min.   :14.0   Min.   :0  
 1st Qu.:3.000   1st Qu.:148.0   1st Qu.: 61.00   1st Qu.:24.0   1st Qu.:0  
 Median :4.000   Median :168.0   Median : 79.00   Median :30.0   Median :0  
 Mean   :3.625   Mean   :170.7   Mean   : 80.57   Mean   :34.3   Mean   :0  
 3rd Qu.:5.000   3rd Qu.:192.0   3rd Qu.: 99.00   3rd Qu.:42.0   3rd Qu.:0  
 Max.   :7.000   Max.   :281.0   Max.   :177.00   Max.   :78.0   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:39.56   1st Qu.: -5.8792   1st Qu.:  42.0  
 Median : 0.00000   Median :41.91   Median : -3.7892   Median : 143.0  
 Mean   : 0.06697   Mean   :40.87   Mean   : -3.4123   Mean   : 343.8  
 3rd Qu.: 0.00000   3rd Qu.:43.30   3rd Qu.:  0.3264   3rd Qu.: 521.0  
 Max.   :45.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt          tmax            tmin           precip           nevada 
 Min.   : 4.00   Min.   :  2.0   Min.   :-53.0   Min.   : 41.00   Min.   :0  
 1st Qu.:10.00   1st Qu.:155.0   1st Qu.: 86.0   1st Qu.: 55.00   1st Qu.:0  
 Median :10.00   Median :184.5   Median :109.0   Median : 66.00   Median :0  
 Mean   :10.29   Mean   :183.3   Mean   :107.9   Mean   : 72.39   Mean   :0  
 3rd Qu.:11.00   3rd Qu.:213.0   3rd Qu.:132.0   3rd Qu.: 85.00   3rd Qu.:0  
 Max.   :12.00   Max.   :336.0   Max.   :219.0   Max.   :144.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   :  0.0000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.0000   1st Qu.:39.85   1st Qu.: -6.949   1st Qu.:  27.0  
 Median :  0.0000   Median :42.27   Median : -3.831   Median :  87.0  
 Mean   :  0.2584   Mean   :41.02   Mean   : -3.940   Mean   : 238.9  
 3rd Qu.:  0.0000   3rd Qu.:43.31   3rd Qu.: -0.558   3rd Qu.: 261.0  
 Max.   :114.0000   Max.   :43.57   Max.   :  4.216   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster07)

   fecha_cnt          tmax            tmin            precip     
 Min.   :1.000   Min.   :-17.0   Min.   :-89.00   Min.   : 0.00  
 1st Qu.:1.000   1st Qu.:114.0   1st Qu.: 16.00   1st Qu.: 4.00  
 Median :2.000   Median :149.0   Median : 41.00   Median : 9.00  
 Mean   :2.517   Mean   :145.3   Mean   : 41.33   Mean   :10.38  
 3rd Qu.:3.000   3rd Qu.:177.0   3rd Qu.: 69.00   3rd Qu.:15.00  
 Max.   :7.000   Max.   :254.0   Max.   :124.00   Max.   :50.00  
     nevada           prof_nieve          longitud        latitud        
 Min.   :0.000000   Min.   :  0.0000   Min.   :28.31   Min.   :-17.7550  
 1st Qu.:0.000000   1st Qu.:  0.0000   1st Qu.:39.47   1st Qu.: -4.6800  
 Median :0.000000   Median :  0.0000   Median :40.95   Median : -2.3567  
 Mean   :0.000881   Mean   :  0.3909   Mean   :40.27   Mean   : -2.5906  
 3rd Qu.:0.000000   3rd Qu.:  0.0000   3rd Qu.:41.84   3rd Qu.:  0.4942  
 Max.   :6.000000   Max.   :503.0000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  81.0  
 Median : 510.0  
 Mean   : 519.6  
 3rd Qu.: 779.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster08)

   fecha_cnt           tmax            tmin           precip           nevada 
 Min.   : 1.000   Min.   : 87.0   Min.   : 56.0   Min.   : 0.000   Min.   :0  
 1st Qu.: 6.000   1st Qu.:236.0   1st Qu.:132.0   1st Qu.: 1.000   1st Qu.:0  
 Median : 7.000   Median :265.0   Median :155.0   Median : 5.000   Median :0  
 Mean   : 7.125   Mean   :266.8   Mean   :156.8   Mean   : 8.109   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:295.0   3rd Qu.:181.0   3rd Qu.:12.000   3rd Qu.:0  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :60.000   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:37.18   1st Qu.: -6.0556   1st Qu.:  32.0  
 Median : 0.00000   Median :39.86   Median : -3.6781   Median :  87.0  
 Mean   : 0.00247   Mean   :38.47   Mean   : -4.2166   Mean   : 287.6  
 3rd Qu.: 0.00000   3rd Qu.:41.62   3rd Qu.:  0.3664   3rd Qu.: 540.0  
 Max.   :35.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2371.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1], dim(df.cluster07)[1], dim(df.cluster08)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06", "cluster07", "cluster08"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.hist(df.cluster07)

if (!empty_nodes) mpr.hist(df.cluster08)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster07)

if (!empty_nodes) mpr.boxplot(df.cluster08)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
  df.cluster07.grouped <- mpr.group_by_geo(df.cluster07)
  df.cluster08.grouped <- mpr.group_by_geo(df.cluster08)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster07.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster08.grouped)

Visualización de 10 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=10)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=10)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)
  df.cluster07 <- subset(df, cluster==7)
  df.cluster08 <- subset(df, cluster==8)
  df.cluster09 <- subset(df, cluster==9)
  df.cluster10 <- subset(df, cluster==10)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster07 <- select(df.cluster07, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster08 <- select(df.cluster08, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster09 <- select(df.cluster09, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster10 <- select(df.cluster10, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax            tmin             precip           nevada 
 Min.   :1.000   Min.   :-42.0   Min.   :-108.00   Min.   : 73.00   Min.   :0  
 1st Qu.:1.000   1st Qu.:109.0   1st Qu.:  38.25   1st Qu.: 81.00   1st Qu.:0  
 Median :2.000   Median :127.0   Median :  59.00   Median : 90.00   Median :0  
 Mean   :2.445   Mean   :126.5   Mean   :  57.15   Mean   : 94.87   Mean   :0  
 3rd Qu.:4.000   3rd Qu.:152.0   3rd Qu.:  80.00   3rd Qu.:104.00   3rd Qu.:0  
 Max.   :6.000   Max.   :239.0   Max.   : 170.00   Max.   :149.00   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :  0.000   Min.   :27.92   Min.   :-17.755   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:41.84   1st Qu.: -8.419   1st Qu.:  42.0  
 Median :  0.000   Median :42.44   Median : -5.645   Median : 251.0  
 Mean   :  6.524   Mean   :41.50   Mean   : -5.291   Mean   : 439.6  
 3rd Qu.:  0.000   3rd Qu.:43.30   3rd Qu.: -2.039   3rd Qu.: 370.0  
 Max.   :892.000   Max.   :43.57   Max.   :  3.182   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin            precip          nevada 
 Min.   : 1.000   Min.   : -8.0   Min.   :-58.00   Min.   :142.0   Min.   :0  
 1st Qu.: 3.000   1st Qu.:113.0   1st Qu.: 52.00   1st Qu.:152.0   1st Qu.:0  
 Median :10.000   Median :131.0   Median : 75.00   Median :167.0   Median :0  
 Mean   : 7.787   Mean   :139.5   Mean   : 76.75   Mean   :183.2   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:154.0   3rd Qu.: 92.00   3rd Qu.:196.0   3rd Qu.:0  
 Max.   :12.000   Max.   :350.0   Max.   :223.00   Max.   :422.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   :  0.000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.000   1st Qu.:40.80   1st Qu.: -8.624   1st Qu.:  68.6  
 Median :  0.000   Median :42.24   Median : -8.411   Median : 261.0  
 Mean   :  5.752   Mean   :41.06   Mean   : -6.466   Mean   : 455.1  
 3rd Qu.:  0.000   3rd Qu.:42.89   3rd Qu.: -3.831   3rd Qu.: 370.0  
 Max.   :607.000   Max.   :43.49   Max.   :  2.825   Max.   :2400.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax             tmin             precip     
 Min.   : 7.00   Min.   :-24.00   Min.   :-110.00   Min.   : 0.00  
 1st Qu.:11.00   1st Qu.: 84.00   1st Qu.:  -2.00   1st Qu.: 7.00  
 Median :12.00   Median :101.00   Median :  17.00   Median :18.00  
 Mean   :11.59   Mean   : 97.71   Mean   :  16.41   Mean   :23.13  
 3rd Qu.:12.00   3rd Qu.:116.00   3rd Qu.:  35.00   3rd Qu.:37.00  
 Max.   :12.00   Max.   :179.00   Max.   :  89.00   Max.   :88.00  
     nevada           prof_nieve          longitud        latitud        
 Min.   :0.000000   Min.   :  0.0000   Min.   :28.31   Min.   :-16.4992  
 1st Qu.:0.000000   1st Qu.:  0.0000   1st Qu.:40.70   1st Qu.: -4.6992  
 Median :0.000000   Median :  0.0000   Median :41.67   Median : -3.1742  
 Mean   :0.001617   Mean   :  0.8346   Mean   :41.18   Mean   : -2.9220  
 3rd Qu.:0.000000   3rd Qu.:  0.0000   3rd Qu.:42.47   3rd Qu.:  0.3264  
 Max.   :3.000000   Max.   :382.0000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.: 510.0  
 Median : 704.0  
 Mean   : 869.7  
 3rd Qu.:1004.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin            precip          nevada 
 Min.   : 7.00   Min.   : 95.0   Min.   :-20.00   Min.   : 0.00   Min.   :0  
 1st Qu.:10.00   1st Qu.:151.0   1st Qu.: 57.00   1st Qu.: 5.00   1st Qu.:0  
 Median :11.00   Median :175.0   Median : 79.00   Median :13.00   Median :0  
 Mean   :10.75   Mean   :175.4   Mean   : 77.55   Mean   :14.66   Mean   :0  
 3rd Qu.:11.00   3rd Qu.:199.0   3rd Qu.: 99.00   3rd Qu.:22.00   3rd Qu.:0  
 Max.   :12.00   Max.   :271.0   Max.   :157.00   Max.   :49.00   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.92   Min.   :-17.7550   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:38.95   1st Qu.: -4.8500   1st Qu.:  47.0  
 Median : 0.00000   Median :40.93   Median : -2.4831   Median : 287.0  
 Mean   : 0.03624   Mean   :40.15   Mean   : -2.6541   Mean   : 450.4  
 3rd Qu.: 0.00000   3rd Qu.:41.98   3rd Qu.:  0.5706   3rd Qu.: 674.0  
 Max.   :59.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax             tmin             precip       nevada 
 Min.   :1.000   Min.   :-53.00   Min.   :-121.00   Min.   : 1   Min.   :0  
 1st Qu.:1.000   1st Qu.:  5.00   1st Qu.: -56.00   1st Qu.:28   1st Qu.:0  
 Median :2.000   Median : 28.00   Median : -38.00   Median :39   Median :0  
 Mean   :2.498   Mean   : 25.85   Mean   : -40.17   Mean   :41   Mean   :0  
 3rd Qu.:3.000   3rd Qu.: 49.00   3rd Qu.: -20.00   3rd Qu.:52   3rd Qu.:0  
 Max.   :6.000   Max.   : 98.00   Max.   :  16.00   Max.   :93   Max.   :0  
   prof_nieve         longitud        latitud            altitud    
 Min.   :   0.00   Min.   :28.31   Min.   :-16.4992   Min.   :  42  
 1st Qu.:   0.00   1st Qu.:40.84   1st Qu.: -4.0103   1st Qu.:1894  
 Median :   0.00   Median :42.47   Median :  0.8842   Median :2230  
 Mean   :  29.99   Mean   :41.66   Mean   : -0.7733   Mean   :2034  
 3rd Qu.:   0.00   3rd Qu.:42.64   3rd Qu.:  1.3656   3rd Qu.:2371  
 Max.   :1834.00   Max.   :43.46   Max.   :  2.4803   Max.   :2535  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt          tmax            tmin            precip         nevada 
 Min.   :1.000   Min.   : 63.0   Min.   :-11.00   Min.   :14.0   Min.   :0  
 1st Qu.:3.000   1st Qu.:148.0   1st Qu.: 61.00   1st Qu.:24.0   1st Qu.:0  
 Median :4.000   Median :168.0   Median : 79.00   Median :30.0   Median :0  
 Mean   :3.625   Mean   :170.7   Mean   : 80.57   Mean   :34.3   Mean   :0  
 3rd Qu.:5.000   3rd Qu.:192.0   3rd Qu.: 99.00   3rd Qu.:42.0   3rd Qu.:0  
 Max.   :7.000   Max.   :281.0   Max.   :177.00   Max.   :78.0   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:39.56   1st Qu.: -5.8792   1st Qu.:  42.0  
 Median : 0.00000   Median :41.91   Median : -3.7892   Median : 143.0  
 Mean   : 0.06697   Mean   :40.87   Mean   : -3.4123   Mean   : 343.8  
 3rd Qu.: 0.00000   3rd Qu.:43.30   3rd Qu.:  0.3264   3rd Qu.: 521.0  
 Max.   :45.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster07)

   fecha_cnt          tmax            tmin           precip           nevada 
 Min.   : 4.00   Min.   :  2.0   Min.   :-53.0   Min.   : 41.00   Min.   :0  
 1st Qu.:10.00   1st Qu.:155.0   1st Qu.: 86.0   1st Qu.: 55.00   1st Qu.:0  
 Median :10.00   Median :184.5   Median :109.0   Median : 66.00   Median :0  
 Mean   :10.29   Mean   :183.3   Mean   :107.9   Mean   : 72.39   Mean   :0  
 3rd Qu.:11.00   3rd Qu.:213.0   3rd Qu.:132.0   3rd Qu.: 85.00   3rd Qu.:0  
 Max.   :12.00   Max.   :336.0   Max.   :219.0   Max.   :144.00   Max.   :0  
   prof_nieve          longitud        latitud           altitud      
 Min.   :  0.0000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:  0.0000   1st Qu.:39.85   1st Qu.: -6.949   1st Qu.:  27.0  
 Median :  0.0000   Median :42.27   Median : -3.831   Median :  87.0  
 Mean   :  0.2584   Mean   :41.02   Mean   : -3.940   Mean   : 238.9  
 3rd Qu.:  0.0000   3rd Qu.:43.31   3rd Qu.: -0.558   3rd Qu.: 261.0  
 Max.   :114.0000   Max.   :43.57   Max.   :  4.216   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster08)

   fecha_cnt          tmax            tmin            precip     
 Min.   :1.000   Min.   :-17.0   Min.   :-89.00   Min.   : 0.00  
 1st Qu.:1.000   1st Qu.:114.0   1st Qu.: 16.00   1st Qu.: 4.00  
 Median :2.000   Median :149.0   Median : 41.00   Median : 9.00  
 Mean   :2.517   Mean   :145.3   Mean   : 41.33   Mean   :10.38  
 3rd Qu.:3.000   3rd Qu.:177.0   3rd Qu.: 69.00   3rd Qu.:15.00  
 Max.   :7.000   Max.   :254.0   Max.   :124.00   Max.   :50.00  
     nevada           prof_nieve          longitud        latitud        
 Min.   :0.000000   Min.   :  0.0000   Min.   :28.31   Min.   :-17.7550  
 1st Qu.:0.000000   1st Qu.:  0.0000   1st Qu.:39.47   1st Qu.: -4.6800  
 Median :0.000000   Median :  0.0000   Median :40.95   Median : -2.3567  
 Mean   :0.000881   Mean   :  0.3909   Mean   :40.27   Mean   : -2.5906  
 3rd Qu.:0.000000   3rd Qu.:  0.0000   3rd Qu.:41.84   3rd Qu.:  0.4942  
 Max.   :6.000000   Max.   :503.0000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  81.0  
 Median : 510.0  
 Mean   : 519.6  
 3rd Qu.: 779.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster09)

   fecha_cnt           tmax            tmin           precip           nevada 
 Min.   : 4.000   Min.   :181.0   Min.   : 70.0   Min.   : 0.000   Min.   :0  
 1st Qu.: 7.000   1st Qu.:251.0   1st Qu.:144.0   1st Qu.: 0.000   1st Qu.:0  
 Median : 8.000   Median :277.0   Median :165.0   Median : 4.000   Median :0  
 Mean   : 7.791   Mean   :277.7   Mean   :166.1   Mean   : 7.984   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:302.0   3rd Qu.:188.0   3rd Qu.:12.000   3rd Qu.:0  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :60.000   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:37.26   1st Qu.: -5.8728   1st Qu.:  27.1  
 Median : 0.00000   Median :39.88   Median : -3.5556   Median :  87.0  
 Mean   : 0.00298   Mean   :38.64   Mean   : -3.8958   Mean   : 279.2  
 3rd Qu.: 0.00000   3rd Qu.:41.61   3rd Qu.:  0.4914   3rd Qu.: 540.0  
 Max.   :35.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster10)

   fecha_cnt          tmax            tmin           precip           nevada 
 Min.   :1.000   Min.   : 87.0   Min.   : 56.0   Min.   : 0.000   Min.   :0  
 1st Qu.:4.000   1st Qu.:210.0   1st Qu.:107.0   1st Qu.: 3.000   1st Qu.:0  
 Median :5.000   Median :225.0   Median :122.0   Median : 8.000   Median :0  
 Mean   :4.659   Mean   :226.3   Mean   :122.3   Mean   : 8.575   Mean   :0  
 3rd Qu.:6.000   3rd Qu.:244.0   3rd Qu.:137.0   3rd Qu.:14.000   3rd Qu.:0  
 Max.   :8.000   Max.   :300.0   Max.   :185.0   Max.   :30.000   Max.   :0  
   prof_nieve           longitud        latitud           altitud      
 Min.   :0.0000000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.:0.0000000   1st Qu.:36.50   1st Qu.: -6.949   1st Qu.:  32.0  
 Median :0.0000000   Median :39.56   Median : -4.023   Median :  87.0  
 Mean   :0.0005932   Mean   :37.85   Mean   : -5.404   Mean   : 318.9  
 3rd Qu.:0.0000000   3rd Qu.:41.66   3rd Qu.: -1.169   3rd Qu.: 567.0  
 Max.   :3.0000000   Max.   :43.57   Max.   :  4.216   Max.   :2371.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1], dim(df.cluster07)[1], dim(df.cluster08)[1], dim(df.cluster09)[1], dim(df.cluster10)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06", "cluster07", "cluster08", "cluster09", "cluster10"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.hist(df.cluster07)

if (!empty_nodes) mpr.hist(df.cluster08)

if (!empty_nodes) mpr.hist(df.cluster09)

if (!empty_nodes) mpr.hist(df.cluster10)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster07)

if (!empty_nodes) mpr.boxplot(df.cluster08)

if (!empty_nodes) mpr.boxplot(df.cluster09)

if (!empty_nodes) mpr.boxplot(df.cluster10)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
  df.cluster07.grouped <- mpr.group_by_geo(df.cluster07)
  df.cluster08.grouped <- mpr.group_by_geo(df.cluster08)
  df.cluster09.grouped <- mpr.group_by_geo(df.cluster09)
  df.cluster10.grouped <- mpr.group_by_geo(df.cluster10)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster07.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster08.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster09.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster10.grouped)